Back to Models

GPT-6.2 Astra APIActive

gpt-6.2-astra

No description available

By:OpenAIInput Type:Output Type:

AI Code With channel availability

The same model is billed by channel discount. Copy a channel code to set your preference.

ChannelCache Hit RateContext
Codex 经济档+89% off
91.0%¥6.336/ M tokens¥31.68/ M tokensRead:¥0.3168/ M tokensWrite:¥7.92/ M tokens1.05M0.0s
Codex 经济档90% off
91.0%¥5.76/ M tokens¥28.8/ M tokensRead:¥0.288/ M tokensWrite:¥7.2/ M tokens1.05M0.0s

Related Models

More models from OpenAI

Compare models from other providers

GPT-6.2 Astra API: price, model ID, and how to call it

Call GPT-6.2 Astra through AI Code With. Use model ID gpt-6.2-astra with 1M context. list price about $8.00 / $40.00 per 1M tokens before channel discounts. About $0.1200 for 100,000 input / 10,000 output tokens at the cheapest live channel.

Model IDgpt-6.2-astra
ProtocolsOpenAI Chat Completions · OpenAI Responses
Context1M
Max output128K

Next: Get API key · Codex setup · Compare OpenAI models · All model prices

Cost calculator

Estimate at the cheapest live channel: $0.8000 / $4.00 per 1M tokens, cache read $0.0400, cache write $1.00. Billed usage follows your prepaid balance.

Estimated cost$0.1200

cURL example

Set model to gpt-6.2-astra. The page slug is only the URL, not the API parameter.

curl https://api.aicodewith.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AICODEWITH_API_KEY" \
  -d '{
    "model": "gpt-6.2-astra",
    "messages": [
      { "role": "user", "content": "What is the meaning of life?" }
    ]
  }'

FAQ

What is the GPT-6.2 Astra model ID?

Send model "gpt-6.2-astra" in the API request. The page path /gpt-6.2-astra is only the URL, not the model parameter.

How do I call the GPT-6.2 Astra API?

Use one AI Code With API key against https://api.aicodewith.ai/v1/chat/completions, and set model to gpt-6.2-astra. Supported protocols: OpenAI Chat Completions / OpenAI Responses. See Codex setup.

How is GPT-6.2 Astra priced?

GPT-6.2 Astra is list price about $8.00 / $40.00 per 1M tokens before channel discounts. The public page shows available channel discounts; billed usage follows your prepaid balance and the live channel. About $0.1200 for 100,000 input / 10,000 output tokens at the cheapest live channel.

How long is the GPT-6.2 Astra context window?

GPT-6.2 Astra has about 1M input context and up to 128K output tokens. Treat that as capacity, not a reason to fill every request.